MrBesen/ffmpeg
1
0
Fork 0
Code Issues Pull Requests Releases Wiki Activity

x86/tx_float: replace fft_sr_avx with fft_sr_fma3

Browse Source 
When the SLOW_GATHER flag was added to the AVX2 version, this
made FMA3-features not enabled on Zen CPUs.
As FMA3 adds 6-7% across all platforms that support it, in
the interest of saving space, this commit removes the AVX
version and replaces it with an FMA3 version.
The only CPUs affected are Sandy Bridge and Bulldozer, which
have AVX support, but no FMA3 support.
In the future, if there's a demand for it, a version of the
function duplicated for AVX can be added.
This commit is contained in:
Lynne 2022-05-21 01:39:12 +02:00
parent 0938ff9701
commit 27cffd16aa
No known key found for this signature in database
GPG Key ID: A2FEA5F03F034464
2 changed files with 9 additions and 9 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

4
libavutil/x86/tx_float.asm
View File

@ -1285,8 +1285,8 @@ FFT_SPLIT_RADIX_DEF 131072
%endmacro
%if ARCH_X86_64
FFT_SPLIT_RADIX_FN avx, float, 0
FFT_SPLIT_RADIX_FN avx, ns_float, 1
FFT_SPLIT_RADIX_FN fma3, float, 0
FFT_SPLIT_RADIX_FN fma3, ns_float, 1
%if HAVE_AVX2_EXTERNAL
FFT_SPLIT_RADIX_FN avx2, float, 0
FFT_SPLIT_RADIX_FN avx2, ns_float, 1

14
libavutil/x86/tx_float_init.c
View File

@ -38,8 +38,8 @@ TX_DECL_FN(fft32, avx)
TX_DECL_FN(fft32_ns, avx)
TX_DECL_FN(fft32, fma3)
TX_DECL_FN(fft32_ns, fma3)
TX_DECL_FN(fft_sr, avx)
TX_DECL_FN(fft_sr_ns, avx)
TX_DECL_FN(fft_sr, fma3)
TX_DECL_FN(fft_sr_ns, fma3)
TX_DECL_FN(fft_sr, avx2)
TX_DECL_FN(fft_sr_ns, avx2)
@ -88,13 +88,13 @@ const FFTXCodelet * const ff_tx_codelet_list_float_x86[] = {
TX_DEF(fft32, FFT, 32, 32, 2, 0, 288, b8_i2, fma3, FMA3, AV_TX_INPLACE, AV_CPU_FLAG_AVXSLOW),
TX_DEF(fft32_ns, FFT, 32, 32, 2, 0, 352, b8_i2, fma3, FMA3, AV_TX_INPLACE | FF_TX_PRESHUFFLE,
AV_CPU_FLAG_AVXSLOW),
#if HAVE_AVX2_EXTERNAL
TX_DEF(fft_sr, FFT, 64, 131072, 2, 0, 256, b8_i2, avx, AVX, 0, AV_CPU_FLAG_AVXSLOW),
TX_DEF(fft_sr_ns, FFT, 64, 131072, 2, 0, 320, b8_i2, avx, AVX, AV_TX_INPLACE | FF_TX_PRESHUFFLE,
TX_DEF(fft_sr, FFT, 64, 131072, 2, 0, 288, b8_i2, fma3, FMA3, 0, AV_CPU_FLAG_AVXSLOW),
TX_DEF(fft_sr_ns, FFT, 64, 131072, 2, 0, 352, b8_i2, fma3, FMA3, AV_TX_INPLACE | FF_TX_PRESHUFFLE,
AV_CPU_FLAG_AVXSLOW),
TX_DEF(fft_sr, FFT, 64, 131072, 2, 0, 288, b8_i2, avx2, AVX2, 0,
#if HAVE_AVX2_EXTERNAL
TX_DEF(fft_sr, FFT, 64, 131072, 2, 0, 320, b8_i2, avx2, AVX2, 0,
AV_CPU_FLAG_AVXSLOW | AV_CPU_FLAG_SLOW_GATHER),
TX_DEF(fft_sr_ns, FFT, 64, 131072, 2, 0, 352, b8_i2, avx2, AVX2, AV_TX_INPLACE | FF_TX_PRESHUFFLE,
TX_DEF(fft_sr_ns, FFT, 64, 131072, 2, 0, 384, b8_i2, avx2, AVX2, AV_TX_INPLACE | FF_TX_PRESHUFFLE,
AV_CPU_FLAG_AVXSLOW | AV_CPU_FLAG_SLOW_GATHER),
#endif
#endif